• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.3
• /
• pp.32-43
• /
• 2002

In this paper, we propose a pattern classification system for digital signal which is based on neural networks. The proposed system consists of two models of neural network. The first part is a wavelet neural network whose role is a feature extraction. For this part, we compare existing models of wavelet networks and propose a new model for feature extraction. The other part is a wavelet network for pattern classification. We modify the structure of previous wavelet network for pattern classification and propose a learning method. The inputs of the pattern classification wavelet network is connection weights, dilation and translation parameters in hidden nodes of feature extraction network. And the output is a class of the signal which is input of feature extraction network. The proposed system is, applied to classification of EEG signal based on frequency.

• The Journal of Society for e-Business Studies
• /
• v.7 no.1
• /
• pp.87-106
• /
• 2002

The behavioral and dynamic implications of an ERP implementation/installation are, to say the least, not well understood. Getting the switches set to enable the ERP software to go live is becoming straightforward. The really difficult part is understanding all of the dynamic interactions that accrue as a consequence. Dynamic causal and connectionist models are employed to facilitate an understanding of the dynamics and to enable control of the information-enhanced processes to take place. The connectionist model ran be analyzing (behind the scenes) the information accesses and transfers and coming If some conclusions about strong linkages that are getting established and what the behavioral implications of those new linkages and information accesses we. Ultimately, the connectionist model will come to an understanding of the dynamic, behavioral implications of the larger ERP implementation/installation per se. The underlying connectionist model will determine information transfers and workflow. Once a map of these two infrastructures is determined by the model, it becomes a relatively easy job for an analyst to suggest improvements in both. Connectionist models start with analog object structures and then use learning to produce mechanisms for managerial problem diagnoses. These mechanisms are neural models with multiple-layer structures that support continuous input/output. Based on earlier work performed and published by the author[10][11], a Connectionist ReasOning and LEarning System(CROLES) is developed that mimics the real-world reasoning infrastructure. Coupled with an explanation subsystem, this system can provide explanations as to why a particular reasoning structure behaved the way it did. Such a system operates in the backgmund, observing what is happening as every information access, every information response coming from each and every intelligent node (whether natural or artificial) operating within the ERP infrastructure is recorded and encoded. The CROLES is also able to transfer all workflows and map these onto the decision-making nodes of the organization.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.49-57
• /
• 2005

In this paper. a CLB-based CPLD low power technology mapping algorithm for trade-off is proposed. To perform low power technology mapping for CPLD, a given Boolean network has to be represented to DAG. The proposed algorithm consists of three step. In the first step, TD(Transition Density) calculation have to be Performed. Total power consumption is obtained by calculating switching activity of each nodes in a DAG. In the second step, the feasible clusters are generated by considering the following conditions : the number of output. the number of input and the number of OR-terms for CLB within a CPLD. The common node cluster merging method, the node separation method, and the node duplication method are used to produce the feasible clusters. The proposed algorithm is examined by using benchmarks in SIS. In the case that the number of OR-terms is 5, the experiments results show reduction in the power consumption by 30.73$\%$ comparing with that of TEMPLA, and 17.11$\%$ comparing with that of PLAmap respectively

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.37 no.1
• /
• pp.83-91
• /
• 2000

This paper presents a new technique to reduce a large interconnect circuit with tens of thousands of elements into the one that is small enough to be analyzed by circuit simulators such as SPICE. This technique takes a fundamentally different approach form the conventional methods based on the interconnect circuit structure analysis and several rules based on the Elmore time constant. The time moments are computed form the circuit consisting of the interconnect circuit and the CMOS gate driver model computed by the AWE technique. Then, the equivalent RC circuit is synthesized from those moments. The characteristics of the driving CMOS gate can be reflected with the high degree of accuracy and the size of the compressed circuit is determined by the number of output nodes regardless of the size of the original interconnect circuits. This technique has been implemented in C language, applied to several interconnect circuits driven by a 0.5${\mu}m$ CMOS gate and the equivalent RC circuits with more than 99% reduction ratio and accuracy with 1 ~ 10% error in therms of propagation delays were obtained.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.9
• /
• pp.953-958
• /
• 2015

Raspberry Pi is a credit card-sized computer with support for a large number of input and output peripherals. This makes it the perfect platform for interaction with many different devices and for usage in a wide range of applications. When combined with Wi-Fi, it can communicate remotely, therefore increasing its suitability for the construction of wireless sensor nodes. In addition, data processing and decision-making can be based on artificial intelligence, what is performed in developed testbed on the example of monitoring and determining the confidence of fire. In this paper, we demonstrated the usage of Raspberry Pi as a sensor web node for fire-safety monitoring in a building. When the UV-flame sensors detect a flame as thin as that of a candle, the Raspberry Pi sends a push-message to notify the assigned smartphone of the on-site situation through the GCM server. A mobile app was developed to provide a real-time video streaming service in order to determine a false alarm. If an emergency occurs, one can immediately call for help.

• Journal of Korea Multimedia Society
• /
• v.9 no.3
• /
• pp.369-376
• /
• 2006

In this paper, we propose an improved fuzzy RBF network which dynamically adjusts the rate of learning by applying the Delta-bar-Delta algorithm in order to improve the learning performance of fuzzy RBF networks. The proposed learning algorithm, which combines the fuzzy C-Means algorithm with the generalized delta learning method, improves its learning performance by dynamically adjusting the rate of learning. The adjustment of the learning rate is achieved by self-generating middle-layered nodes and by applying the Delta-bar-Delta algorithm to the generalized delta learning method for the learning of middle and output layers. To evaluate the learning performance of the proposed RBF network, we used 40 identifiers extracted from a container image as the training data. Our experimental results show that the proposed method consumes less training time and improves the convergence of teaming, compared to the conventional ART2-based RBF network and fuzzy RBF network.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.4
• /
• pp.1976-1981
• /
• 2013

In this paper, we propose a frequency-domain interference cancellation algorithm for direct-sequence spread spectrum systems. In the previously proposed frequency-domain interference cancellation algorithms that protocol defines the rules concerning the collection of means of Transmission Control Protocol (TCP: Transmission Control Protocol) is the most widely used in the transport layer. Two-way traffic through the network path to the same end-to-end transfer of data in the opposite direction between pairs of nodes are infused with two or more TCP connection using the network traffic patterns from the exchanger and routers share results of approval. Per-flow input/output structure of matter using the LTS online reaction when evaluated as this is the most important factor. TCP-MT when the connection duration is one of the largest performance gains.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.34 no.2
• /
• pp.73-84
• /
• 1992

The TIDE, finite element model for the simulation of tidal flow in shallow sea was tested for its applicability at the Saemangeum area. Several pre and post processors were developed to facilitate handling of the complicated and large amount of input and output data for the model developed. Also an operation scheme to run the model and the processors were established. As a result of calibration test using the observed data collected at 9 points within the region, linearlized friction coefficients were adjusted to be ranged 0.0027~0.0072, and water depths below the mean sea level at every nodes were changed to be increased generally by 1 meter. Comparisons of tidal velocities between the observed and the simulated for the 5 stations were made and obtained the result that the average relative error between simulated and observed tidal velocities was 11% for the maximum velocities and 22% for the minimum, and the absolute errors were less than 0.2m/sec. Also it was found that the average R.M.S. error between the velocities of observed and simulated was 0.119 m/sec and the average correlation coefficient was 0.70 showing close agreement. Another comparison test was done to show the result that R.M.S. error between the simulated and the observed tidal elevations at the 4 stations was 0.476m in average and the correlation coefficients were ranged 0.96~0.99. Though the simulated tidal circulation pattern in the region was well agreed with the observed, the simulated tidal velocities and elevations for specific points showed some errors with the observed. It was thought that the errors mainly due to the characteristics of TIDE Model which was developed to solve only with the linearized scheme. Finally it was concluded that, to improve the simulation results by the model, a new attempt to develop a fully nonlinear model as well as further calibration and the more reasonable generation of finite element grid would be needed.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.2
• /
• pp.65-72
• /
• 1990

The potential of neural networks for the recognition of the printed Korean characters is examined. In spite of good classification capability of neural networks, it is difficult to train a neural network to recognize Korean characters. The difficulty is due to a large number of Korean characters, the similarities among the characters, and the large number of data from the character images. To reduce the input image data, DC components are extracted from each input images. These preprocessed data are used as input to the neural network. The output nodes are composed to represent the characteristics of Korean characters. A MLP (multilayer perceptron) with one hidden layer was trained with a modified BEP algorithm, This method gives good recognition rate for the standard positioned characters of more than 2,300. The result shows that neural networks are well suited for the recognition of printed Korean characters.

• Journal of KIISE:Software and Applications
• /
• v.28 no.12
• /
• pp.875-884
• /
• 2001

Although the self organizing map (SOM) is widely utilized in such fields of data visualization and topology preserving mapping, since it should have the topology fixed before trained, it has some shortcomings that it is difficult to apply it to practical problems, and classification capability is quite low despite better clustering performance. To overcome these points this paper proposes the dynamic topology preserving self-organizing map(DTSOM) that dynamically splits the output nodes on the map and trains them, and attempts to improve the classification capability by combining multiple DTSOMs K-Winner method has been applied to combine DTSOMs which produces K outputs with winner node selection method. This produces even better performance than the conventional combining methods such as majority voting weighting, BKS Bayesian, Borda, Condorect and reliability sum. DTSOM remedies the shortcoming of determining the topology in advance, and the classification rate increases significantly by combing multiple maps trained with different features. Experimental results with handwritten digit recognition indicate that the proposed method works out to problems of conventional SOM effectively so to improve the classification rate to 98.1%.